Generate new faces using Generative Adversarial Networks
using GANs network to generate new images of faces that look as realistic as possible! The project is broken down into a series of tasks from loading in data to defining and training adversarial networks. At the end of the project, you'll be able to visualize the results of your trained Generator to see how it performs; your generated samples should look like fairly realistic faces with small amounts of noise. the goal of the project is to Generate new faces using Generative Adversarial Networks (GANs).The model is trained on the CelebFaces Attributes Dataset. At the end of the project, I was able to visualize the results of my trained Generator to see how it performsed; my generated samples looked like fairly realistic faces with small amounts of noise.
- Visualize the CelebA Data
- Pre-process and Load the Data
- Define the Model: the generator and the discriminator
- Initialize the weights of your networks
- build the model and define the hyperparameters
- calculate the real and fake losses and optimizing
- training the model and validating it
- generate samples from the training
1- conda create --name face_generation python=3.6 2- activate face_generation Install a few required pip packages, which are specified in the requirements text file. 3- pip install -r requirements.txt